Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    say "001"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plements
    -0.07
     Guang
    -0.07
     sandwich
    -0.06
     swaps
    -0.06
     Name
    -0.06
     detector
    -0.06
     lovers
    -0.06
    ẵ
    -0.06
     Mills
    -0.06
    Only
    -0.06
    POSITIVE LOGITS
    _ON
    0.07
    .LogError
    0.07
    (StringUtils
    0.06
    .t
    0.06
     xAxis
    0.06
    ﾐ
    0.06
    corlib
    0.06
    .PORT
    0.06
    �
    0.06
    uspendLayout
    0.06
    Act Density 0.020%

    No Known Activations